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. 90084
    Prev
    Next
    INDEX
    Explanations

    receipt

    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
     lob
    -0.07
     hardly
    -0.07
     sumin
    -0.07
     Crystal
    -0.07
    .web
    -0.07
     rewritten
    -0.07
    inks
    -0.07
     capacit
    -0.07
     loader
    -0.07
     GP
    -0.07
    POSITIVE LOGITS
    tin
    0.09
     tann
    0.08
    slu
    0.08
    ṣẹ
    0.08
     Victor
    0.08
     tin
    0.08
     Slov
    0.07
    boom
    0.07
     impor
    0.07
    Victor
    0.07
    Activations Density 0.014%

    No Known Activations