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. 11622
    Prev
    Next
    INDEX
    Explanations

    v

    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
     inland
    -0.08
     alip
    -0.08
     deny
    -0.08
     enumerable
    -0.07
    asured
    -0.07
     siph
    -0.07
     ope
    -0.07
     denying
    -0.07
    (element
    -0.07
     parap
    -0.07
    POSITIVE LOGITS
     diplomat
    0.08
    _mag
    0.08
     blazer
    0.08
     Coy
    0.07
     accommodating
    0.07
     reset
    0.07
     marcador
    0.07
    bonne
    0.07
    Accommodation
    0.07
    izung
    0.07
    Activations Density 0.011%

    No Known Activations