Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 120168
    Prev
    Next
    INDEX
    Explanations

    destination

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    от
    -0.08
     збор
    -0.08
    (axis
    -0.07
     招
    -0.07
     compartment
    -0.07
     dise
    -0.07
    iefer
    -0.07
    33
    -0.07
     hang
    -0.07
     disf
    -0.06
    POSITIVE LOGITS
    INATION
    0.10
    ataire
    0.08
    定位
    0.08
     Market
    0.08
     Aw
    0.08
    (destination
    0.07
     urs
    0.07
    inations
    0.07
    etele
    0.07
     Sid
    0.07
    Activations Density 0.008%

    No Known Activations