© 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. 48515
    Prev
    Next
    INDEX
    Explanations

    mist

    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
    АМ
    -0.07
    ам
    -0.07
    Aug
    -0.07
    Cab
    -0.07
    am
    -0.07
    C
    -0.07
    itating
    -0.07
     Aug
    -0.07
     captain
    -0.07
    acoes
    -0.07
    POSITIVE LOGITS
    ake
    0.16
    akes
    0.15
    akeup
    0.10
    aken
    0.09
    irebase
    0.09
    embrance
    0.08
    ę
    0.08
    unktion
    0.08
    AKE
    0.08
    heastern
    0.08
    Activations Density 0.002%

    No Known Activations