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. 67787
    Prev
    Next
    INDEX
    Explanations

    impossible

    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
    SG
    -0.08
     Patreon
    -0.08
    bur
    -0.08
    Mol
    -0.08
     Solic
    -0.08
    STM
    -0.08
    Ian
    -0.08
    BR
    -0.07
     bye
    -0.07
     blag
    -0.07
    POSITIVE LOGITS
     impossible
    0.09
     feats
    0.08
    掉
    0.08
     feat
    0.07
    viol
    0.07
     raisonn
    0.07
    เลย
    0.07
     hur
    0.07
    hafte
    0.07
     pasti
    0.07
    Activations Density 0.008%

    No Known Activations