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. 7-RESID-POST-AA
    6. 1690
    Prev
    Next
    INDEX
    Explanations

    strictly, absolute

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gravel
    -0.08
    istro
    -0.08
    ที่จะ
    -0.07
     �
    -0.07
     REC
    -0.07
     идет
    -0.07
    .Merge
    -0.07
     сер
    -0.07
     Tl
    -0.07
     listed
    -0.07
    POSITIVE LOGITS
     sahaja
    0.08
     megh
    0.08
     Carter
    0.07
     argumentative
    0.07
     ou
    0.07
    .container
    0.07
    .Lo
    0.07
    atus
    0.07
    ileged
    0.07
    òs
    0.07
    Activations Density 0.449%

    No Known Activations