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. 88037
    Prev
    Next
    INDEX
    Explanations

    consistency

    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
     Label
    -0.08
    .Locale
    -0.08
     farms
    -0.07
    park
    -0.07
     Birds
    -0.07
     yer
    -0.07
     ovens
    -0.07
     hens
    -0.07
    .Date
    -0.07
    Context
    -0.07
    POSITIVE LOGITS
     густ
    0.10
    Verdana
    0.09
     легче
    0.09
    ાઢ
    0.09
    густ
    0.09
     clog
    0.08
     workable
    0.08
    爽
    0.08
     thicker
    0.08
     плот
    0.08
    Activations Density 0.011%

    No Known Activations