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. 103043
    Prev
    Next
    INDEX
    Explanations

    im

    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
    óstico
    -0.08
     לל
    -0.08
    רג
    -0.08
     chịu
    -0.07
    ográfica
    -0.07
    辱
    -0.07
     intimately
    -0.07
    ying
    -0.07
    为了
    -0.07
     ínt
    -0.07
    POSITIVE LOGITS
    fc
    0.09
    .fc
    0.09
    Keyword
    0.09
    FC
    0.08
     fed
    0.08
     cannabino
    0.08
    keyword
    0.08
     keyword
    0.07
     emoji
    0.07
    psc
    0.07
    Activations Density 0.081%

    No Known Activations