© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 96971
    Prev
    Next
    INDEX
    Explanations

    say "+"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beschreven
    -0.10
    anken
    -0.09
    haben
    -0.09
    ercer
    -0.09
    imia
    -0.08
     descr
    -0.08
     beschrieben
    -0.08
    uminen
    -0.08
    ervis
    -0.08
    onis
    -0.08
    POSITIVE LOGITS
     ลง
    0.09
    (-
    0.09
    ,-
    0.08
     Rule
    0.08
    остей
    0.08
    =-
    0.08
     For
    0.08
    /Documents
    0.07
     nor
    0.07
     rule
    0.07
    Activations Density 0.051%

    No Known Activations