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. 12301
    Prev
    Next
    INDEX
    Explanations

    storytelling

    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
     routinely
    -0.08
    版权所有
    -0.08
     cello
    -0.08
     passionate
    -0.08
     apreciar
    -0.08
    ാ�
    -0.07
    Unicode
    -0.07
     sensibilidad
    -0.07
    _AXI
    -0.07
    Lub
    -0.07
    POSITIVE LOGITS
     survival
    0.13
     superviv
    0.12
     Survival
    0.12
     contestants
    0.11
     survive
    0.11
     Survivor
    0.11
     surv
    0.11
     survivor
    0.11
     surviv
    0.11
     survivors
    0.11
    Activations Density 0.033%

    No Known Activations