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. 12676
    Prev
    Next
    INDEX
    Explanations

    Human

    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
    Pkt
    -0.09
    ativer
    -0.08
    _pkt
    -0.08
    ATIVE
    -0.08
    ixir
    -0.07
    ixar
    -0.07
     два
    -0.07
     irrigation
    -0.07
    alias
    -0.07
     woody
    -0.07
    POSITIVE LOGITS
    /
    0.09
     Representatives
    0.09
     девушки
    0.08
    /non
    0.08
    /world
    0.08
    /F
    0.08
     yok
    0.08
    -like
    0.08
    女孩
    0.08
     lain
    0.08
    Activations Density 0.010%

    No Known Activations