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. 43470
    Prev
    Next
    INDEX
    Explanations

    but

    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
    517
    -0.09
     wings
    -0.08
    abil
    -0.08
     Werner
    -0.07
    ouw
    -0.07
    arne
    -0.07
    경
    -0.07
    509
    -0.07
    541
    -0.07
    535
    -0.07
    POSITIVE LOGITS
    गा
    0.09
    扩大
    0.08
    ,%
    0.08
    გენ
    0.08
     gbas
    0.08
     vegnir
    0.08
    ғары
    0.08
    -expand
    0.07
     sement
    0.07
     oceans
    0.07
    Activations Density 0.001%

    No Known Activations