© 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. 23-RESID-POST-AA
    11. 51375
    Prev
    Next
    INDEX
    Explanations

    say pass

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Packing
    -0.09
     aussch
    -0.08
     Purch
    -0.08
     Packaging
    -0.08
    Packing
    -0.08
     Blank
    -0.08
     blanks
    -0.08
     рах
    -0.08
     Advocate
    -0.08
    _blank
    -0.08
    POSITIVE LOGITS
     passen
    0.13
     pass
    0.13
     passes
    0.12
     પાસ
    0.11
     पास
    0.11
    passes
    0.11
     passe
    0.11
    Pass
    0.11
     پاس
    0.11
    _pass
    0.11
    Activations Density 0.010%

    No Known Activations