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. 45338
    Prev
    Next
    INDEX
    Explanations

    decoding text

    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
    Criterion
    -0.09
     Criterion
    -0.09
     Guide
    -0.08
    riterion
    -0.08
    cgi
    -0.08
     Scaffold
    -0.08
     Criteria
    -0.08
    criterion
    -0.08
     Scope
    -0.07
     Mathf
    -0.07
    POSITIVE LOGITS
     decoded
    0.14
    decoded
    0.12
     decrypted
    0.12
     decipher
    0.12
     plaintext
    0.11
    Decoded
    0.11
     decode
    0.11
    crypted
    0.11
    Decode
    0.11
     traduz
    0.11
    Activations Density 0.018%

    No Known Activations