© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 19163
    Prev
    Next
    INDEX
    Explanations

    "re" prefix

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    'etiti
    -0.09
    veless
    -0.08
    'Ar
    -0.08
    ampaikan
    -0.08
     URLs
    -0.08
    'ihi
    -0.08
     DISCLAIMED
    -0.08
     proxies
    -0.08
     арас
    -0.08
    ymph
    -0.08
    POSITIVE LOGITS
     rewriting
    0.18
     reorgan
    0.18
     rearr
    0.17
     restructure
    0.16
     rewrite
    0.16
     completing
    0.16
     restructuring
    0.15
     Completing
    0.15
     regroup
    0.14
     transform
    0.14
    Activations Density 0.038%

    No Known Activations