© 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. 48108
    Prev
    Next
    INDEX
    Explanations

    equ

    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
    grid
    -0.09
    sm
    -0.08
    bj
    -0.08
    -sm
    -0.08
     végét
    -0.08
     kiri
    -0.08
    process
    -0.08
     devant
    -0.08
    �
    -0.08
    �
    -0.07
    POSITIVE LOGITS
    िव
    0.13
    િવ
    0.12
    ிவ
    0.11
    ಿವ
    0.11
    ിവ
    0.11
    iv
    0.10
    িভ
    0.09
    ив
    0.09
     posled
    0.09
    ivalent
    0.09
    Activations Density 0.047%

    No Known Activations