© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91259
    Prev
    Next
    INDEX
    Explanations

    Nuclear fission

    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
    Emoji
    -0.10
     competencias
    -0.10
     objectively
    -0.09
     অনুস
    -0.09
     ვიზ
    -0.09
     emoji
    -0.09
     Emoji
    -0.09
     વિડ
    -0.09
     panor
    -0.09
     emojis
    -0.09
    POSITIVE LOGITS
     plut
    0.12
     neutron
    0.10
     aluminum
    0.10
     Aluminum
    0.09
     Ingen
    0.09
    ROL
    0.09
     silicon
    0.09
     uranium
    0.08
     оруж
    0.08
    warz
    0.08
    Activations Density 0.007%

    No Known Activations