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. 102843
    Prev
    Next
    INDEX
    Explanations

    complement

    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
    hile
    -0.08
     എത്ത
    -0.08
     അന്ത
    -0.08
    unia
    -0.08
    -0.07
    .ACC
    -0.07
     നിങ്ങ
    -0.07
     Node
    -0.07
    .chapter
    -0.07
    _misc
    -0.07
    POSITIVE LOGITS
    Stars
    0.10
     stars
    0.09
    Complement
    0.09
     complements
    0.08
    Connections
    0.08
    Peers
    0.08
     complemento
    0.08
    Blocked
    0.08
     complement
    0.08
    Blacklist
    0.08
    Activations Density 0.007%

    No Known Activations