Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 77737
    Prev
    Next
    INDEX
    Explanations

    Code with brackets and dots

    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
     depleted
    -0.08
     cruising
    -0.08
     speed
    -0.08
     steels
    -0.08
    _PUR
    -0.08
     hosp
    -0.08
    _SSL
    -0.08
    _TLS
    -0.08
     wander
    -0.07
     meeting
    -0.07
    POSITIVE LOGITS
    prefix
    0.11
     Prefix
    0.10
     prefix
    0.10
    (prefix
    0.10
     prefixes
    0.10
    _prefix
    0.09
    Prefixes
    0.09
    _PREFIX
    0.09
    Prefix
    0.09
    .prefix
    0.09
    Activations Density 0.004%

    No Known Activations