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. 420
    Prev
    Next
    INDEX
    Explanations

    Informal writing

    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
    irse
    -0.08
    .Measure
    -0.08
    řit
    -0.08
    getahuan
    -0.08
    }}>
    -0.08
     qualsevol
    -0.08
     arbete
    -0.08
    毫米
    -0.08
     praises
    -0.08
     [{"
    -0.08
    POSITIVE LOGITS
    Cipher
    0.11
     cipher
    0.10
    谜
    0.10
     clues
    0.10
    cipher
    0.09
     Cipher
    0.08
     Puzzle
    0.08
     decipher
    0.08
     puzzle
    0.08
    Palindrome
    0.08
    Activations Density 0.145%

    No Known Activations