© 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. 48680
    Prev
    Next
    INDEX
    Explanations

    The

    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
    -Code
    -0.09
    -this
    -0.09
     aggreg
    -0.08
     froide
    -0.08
    inah
    -0.08
    -K
    -0.08
    -Core
    -0.08
     hiss
    -0.07
     BELOW
    -0.07
    -head
    -0.07
    POSITIVE LOGITS
     രക്ഷ
    0.08
     individuele
    0.08
     hogere
    0.08
     posame
    0.08
    Individual
    0.08
     voorkomt
    0.08
    ‍ന്ന്
    0.08
     അധ
    0.08
     individuais
    0.08
     Reef
    0.08
    Activations Density 0.001%

    No Known Activations