© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 26433
    Prev
    Next
    INDEX
    Explanations

    annual income

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _arg
    -0.08
    Ao
    -0.08
    RGB
    -0.07
    _poly
    -0.07
     Warfare
    -0.07
     ослож
    -0.07
     वक्त
    -0.07
     Subway
    -0.07
    Ve
    -0.07
    wali
    -0.07
    POSITIVE LOGITS
    收益
    0.12
     jähr
    0.12
     annually
    0.12
     revenues
    0.12
     yearly
    0.11
     jährlich
    0.11
     annual
    0.10
     revenus
    0.10
     monthly
    0.10
     rendement
    0.10
    Activations Density 0.021%

    No Known Activations