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. 27795
    Prev
    Next
    INDEX
    Explanations

    conditional statements

    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
    ,不过
    -0.09
    纳
    -0.09
    ړې
    -0.08
    掉
    -0.08
     حرفه
    -0.08
     기타
    -0.07
     Kann
    -0.07
     jeung
    -0.07
     chl
    -0.07
    Promises
    -0.07
    POSITIVE LOGITS
    foundation
    0.09
     فإن
    0.08
     Dependency
    0.08
    SV
    0.08
    SJ
    0.07
    innovation
    0.07
     infinite
    0.07
    Gir
    0.07
     automáticamente
    0.07
    cony
    0.07
    Activations Density 0.137%

    No Known Activations