© 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. 19128
    Prev
    Next
    INDEX
    Explanations

    acute

    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
    mg
    -0.09
    the
    -0.09
    sticky
    -0.08
    such
    -0.08
    poro
    -0.08
    ofs
    -0.08
    mh
    -0.08
    руч
    -0.08
    snake
    -0.08
    spam
    -0.08
    POSITIVE LOGITS
     (<
    0.17
     (>
    0.14
    -angle
    0.13
    _angle
    0.12
    (<
    0.12
    -feira
    0.11
     (~
    0.11
     angles
    0.11
    _angles
    0.11
     جدًا
    0.10
    Activations Density 0.004%

    No Known Activations