© 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. 18694
    Prev
    Next
    INDEX
    Explanations

    acquaintances

    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
     ratio
    -0.11
     Ratio
    -0.10
     resíduos
    -0.10
    ratio
    -0.10
    面积
    -0.09
     volum
    -0.09
    _STACK
    -0.09
    Ratio
    -0.09
     voltage
    -0.09
    _resize
    -0.09
    POSITIVE LOGITS
     acquaintances
    0.19
     friendships
    0.16
     acquaintance
    0.16
     everyone
    0.16
    Everyone
    0.15
     friendship
    0.15
     everybody
    0.15
    everyone
    0.14
     who
    0.14
     whom
    0.14
    Activations Density 0.029%

    No Known Activations