Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 1683
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fear
    -0.08
    uyo
    -0.08
    .Shapes
    -0.08
    아이
    -0.08
     여부
    -0.08
     vocational
    -0.07
     வர
    -0.07
    urge
    -0.07
    een
    -0.07
     सम्म
    -0.07
    POSITIVE LOGITS
    _internal
    0.07
     Ach
    0.07
     Const
    0.07
    0.07
     Sin
    0.07
     Liga
    0.07
     bombe
    0.07
     planes
    0.07
    -total
    0.07
     nowhere
    0.07
    Activations Density 0.000%

    No Known Activations