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. 53674
    Prev
    Next
    INDEX
    Explanations

    Calls to action

    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
     dumped
    -0.08
    _RAM
    -0.08
     springfox
    -0.08
    .dump
    -0.08
     turret
    -0.08
     contracted
    -0.07
    Diag
    -0.07
     jout
    -0.07
     dump
    -0.07
     العاصمة
    -0.07
    POSITIVE LOGITS
     urging
    0.13
     CTA
    0.11
     encourages
    0.11
     actionable
    0.11
     encourage
    0.11
     urges
    0.11
     encouraging
    0.11
     urged
    0.10
     thúc
    0.10
    cta
    0.10
    Activations Density 0.029%

    No Known Activations