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. 77186
    Prev
    Next
    INDEX
    Explanations

    containers

    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
    reject
    -0.08
     işe
    -0.08
     Obviously
    -0.08
    insp
    -0.08
    textfield
    -0.07
    ğe
    -0.07
     напомина
    -0.07
    Clearly
    -0.07
     диск
    -0.07
     مبلغ
    -0.07
    POSITIVE LOGITS
    /day
    0.09
    -count
    0.08
    ోలు
    0.08
    ами
    0.08
     クロ
    0.08
    uses
    0.07
     procuram
    0.07
    ấ
    0.07
    ales
    0.07
    amentos
    0.07
    Activations Density 0.025%

    No Known Activations