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. 65063
    Prev
    Next
    INDEX
    Explanations

    chain

    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
     committed
    -0.08
     steadfast
    -0.08
     Mississippi
    -0.08
     déi
    -0.08
    home
    -0.08
    pakket
    -0.07
     kingdoms
    -0.07
    尽
    -0.07
     નિવ
    -0.07
     GUID
    -0.07
    POSITIVE LOGITS
     funky
    0.08
     rhythmic
    0.08
    crypt
    0.08
     collapsing
    0.08
    Encryption
    0.08
    _mux
    0.08
     stimulus
    0.08
     трен
    0.08
     policial
    0.08
     Width
    0.08
    Activations Density 0.002%

    No Known Activations