© 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. 18352
    Prev
    Next
    INDEX
    Explanations

    groups

    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
     واک
    -0.08
     bowed
    -0.08
     Höhe
    -0.08
    ẹrẹ
    -0.07
     proti
    -0.07
     Pence
    -0.07
    atra
    -0.07
    ství
    -0.07
     mounting
    -0.07
    bow
    -0.07
    POSITIVE LOGITS
     grupos
    0.28
     group
    0.28
     समूह
    0.28
     grupo
    0.28
     groupe
    0.28
     groupes
    0.28
     groups
    0.27
     grupper
    0.27
     گروه
    0.26
    _group
    0.26
    Activations Density 0.116%

    No Known Activations