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. 56277
    Prev
    Next
    INDEX
    Explanations

    adjust

    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
    ateľ
    -0.08
     اختیار
    -0.07
     turbine
    -0.07
     Tips
    -0.07
    All
    -0.07
     following
    -0.07
     hints
    -0.07
     vurder
    -0.07
    meter
    -0.07
     UAV
    -0.07
    POSITIVE LOGITS
     castell
    0.08
     rodzaju
    0.08
    isay
    0.08
    .creation
    0.08
     horr
    0.08
     restrictive
    0.08
     horrifying
    0.08
     savage
    0.08
     horrific
    0.08
     sådan
    0.08
    Activations Density 0.000%

    No Known Activations