© 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. 6115
    Prev
    Next
    INDEX
    Explanations

    随

    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
    之
    -0.11
    之一
    -0.09
    allback
    -0.08
    ometr
    -0.08
    olla
    -0.08
     �
    -0.08
     производства
    -0.08
    ungi
    -0.08
    osa
    -0.08
     такой
    -0.08
    POSITIVE LOGITS
    需要
    0.11
    需
    0.10
     missä
    0.10
    叫
    0.09
    hether
    0.09
     need
    0.09
     needed
    0.09
     kailangan
    0.09
     naslov
    0.09
     neces
    0.09
    Activations Density 0.001%

    No Known Activations