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. 48205
    Prev
    Next
    INDEX
    Explanations

    string splitting in programming

    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
    -Al
    -0.08
    Al
    -0.08
     തിരിച്ച
    -0.07
    VG
    -0.07
     bộ
    -0.07
     किश
    -0.07
     पहचान
    -0.07
     social
    -0.07
    _AL
    -0.07
    _al
    -0.07
    POSITIVE LOGITS
    óticos
    0.08
     Maintaining
    0.08
     expediente
    0.08
     nào
    0.07
    ".$_
    0.07
    udiant
    0.07
     aber
    0.07
     summoned
    0.07
     NSNumber
    0.07
     Bind
    0.07
    Activations Density 0.000%

    No Known Activations