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. 11-RESID-POST-AA
    6. 101716
    Prev
    Next
    INDEX
    Explanations

    Math and functions

    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
     niv
    -0.08
    ల్ప
    -0.08
     denying
    -0.07
     מלא
    -0.07
     godt
    -0.07
    ెంబ
    -0.07
     fejl
    -0.07
     Konz
    -0.07
     راز
    -0.07
    ៩
    -0.07
    POSITIVE LOGITS
     reti
    0.08
     kills
    0.08
    ,但是
    0.08
    prit
    0.08
    ~,
    0.08
    prits
    0.07
     cute
    0.07
    ですが
    0.07
     하지만
    0.07
    하지만
    0.07
    Activations Density 0.386%

    No Known Activations