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. 7-RESID-POST-AA
    6. 2005
    Prev
    Next
    INDEX
    Explanations

    rotate replace

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     സംവിധാനം
    -0.09
     Sherman
    -0.08
     arrangement
    -0.08
     along
    -0.07
     IF
    -0.07
     സംവിധ
    -0.07
     IDM
    -0.07
     IM
    -0.07
     함께
    -0.07
     Igor
    -0.07
    POSITIVE LOGITS
    �
    0.08
    (Value
    0.08
     Unicorn
    0.08
    (Un
    0.08
     Exceptions
    0.08
    (Character
    0.08
     volunt
    0.08
     gettext
    0.07
    913
    0.07
    (Icons
    0.07
    Activations Density 0.001%

    No Known Activations