Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 58446
    Prev
    Next
    INDEX
    Explanations

    alpha

    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
     VAC
    -0.08
    ોએ
    -0.08
     poss
    -0.08
     astronaut
    -0.08
    优惠
    -0.08
     нак
    -0.08
     astronom
    -0.07
    馆
    -0.07
     [$
    -0.07
     સૌ
    -0.07
    POSITIVE LOGITS
    ilage
    0.08
     shower
    0.08
    np
    0.08
    (np
    0.08
    ref
    0.08
    sin
    0.08
     pomaga
    0.08
    .ref
    0.08
    염
    0.07
     royale
    0.07
    Activations Density 0.000%

    No Known Activations