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. 65144
    Prev
    Next
    INDEX
    Explanations

    Sartre

    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
    _LOOP
    -0.09
     rhythm
    -0.09
    _ADDRESS
    -0.09
    ോഷ്യ
    -0.08
     address
    -0.08
    _THRESHOLD
    -0.08
     QUESTION
    -0.08
    _NOTICE
    -0.08
    _NOTIFY
    -0.07
    .G
    -0.07
    POSITIVE LOGITS
    pendent
    0.08
     colomb
    0.08
    ]])↵
    0.07
     MDR
    0.07
    lel
    0.07
    merci
    0.07
     Mafia
    0.07
     दश
    0.07
     خیر
    0.07
     mandatory
    0.07
    Activations Density 0.002%

    No Known Activations