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. 117487
    Prev
    Next
    INDEX
    Explanations

    Code syntax

    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
    _dash
    -0.07
     fra
    -0.07
    ident
    -0.07
    乃
    -0.07
    /entities
    -0.07
    _sig
    -0.07
    τε
    -0.07
     Sch
    -0.07
    öl
    -0.06
    replacement
    -0.06
    POSITIVE LOGITS
     anytime
    0.10
     etdir
    0.09
    habt
    0.09
     continuously
    0.09
     continually
    0.08
     Throughout
    0.08
    .")↵↵
    0.08
     chod
    0.08
    ორმ
    0.08
    Initially
    0.08
    Activations Density 0.014%

    No Known Activations