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. 90824
    Prev
    Next
    INDEX
    Explanations

    corruption

    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
     respir
    -0.08
     iodine
    -0.08
    .dropout
    -0.08
     virgin
    -0.07
    涨
    -0.07
     Betrieb
    -0.07
     pun
    -0.07
     taper
    -0.07
    lager
    -0.07
    /me
    -0.07
    POSITIVE LOGITS
     initiatives
    0.08
    �
    0.08
     allegations
    0.08
     amassed
    0.08
     scandals
    0.07
    .Entry
    0.07
    -minded
    0.07
    ailable
    0.07
    -filled
    0.07
     therein
    0.07
    Activations Density 0.009%

    No Known Activations