© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 5944
    Prev
    Next
    INDEX
    Explanations

    good

    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
    	done
    -0.08
    basename
    -0.08
     impactful
    -0.08
    imized
    -0.08
    aceted
    -0.08
    enced
    -0.08
    baz
    -0.08
    anged
    -0.07
    earched
    -0.07
    initialize
    -0.07
    POSITIVE LOGITS
     detail
    0.11
     mesure
    0.11
     measure
    0.11
    _need
    0.10
     ανάγκ
    0.10
     need
    0.10
     accordance
    0.09
     esteem
    0.09
     consequence
    0.09
     detalle
    0.09
    Activations Density 0.019%

    No Known Activations