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. 29869
    Prev
    Next
    INDEX
    Explanations

    article "the"

    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
     direção
    -0.09
     matem
    -0.08
     вправ
    -0.08
     capit
    -0.08
    ∞
    -0.08
    /math
    -0.08
    �
    -0.08
     matemática
    -0.08
     recip
    -0.07
     omg
    -0.07
    POSITIVE LOGITS
     पता
    0.09
     antivirus
    0.09
     DHCP
    0.09
     обнаруж
    0.08
     footprint
    0.08
     известно
    0.08
     Antivirus
    0.08
     गतिविध
    0.08
     पहचान
    0.08
     folklore
    0.08
    Activations Density 0.005%

    No Known Activations